Nanonets-OCR-s-AIO-GGUF

Nanonets-OCR-s-AIO-GGUF

Nanonets-OCR-s is a state-of-the-art image-to-markdown OCR model that transforms complex documents into structured markdown with intelligent content recognition and semantic tagging. It goes beyond simple text extraction by accurately recognizing LaTeX equations, images, signatures, watermarks, checkboxes, and complex tables, making the output highly suitable for downstream processing by Large Language Models (LLMs). Built on the Qwen2.5-VL-3B Visual-Language Model and trained on over 250,000 diverse pages—including research papers, legal and financial documents, healthcare forms, and more—the model excels in preserving document structure and semantic context. It supports intelligent tagging of visual elements and special components, enabling efficient document understanding and automation in academic, legal, healthcare, and corporate workflows.

Model Files

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):